Aug 2026· Journal of Intelligent Decision Making and Information Science· Vol 3, pp. 542-568· 0 citations· 34 references
TL;DR
Comparisons of six methods covering two statistical and four AI algorithms for forecasting electricity demand confirm that data richness particularly hourly granularity is a decisive factor in forecasting accuracy, and that deep learning models require substantial data volumes to outperform statistical baselines.
Abstract
Electricity is a vital resource that powers modern society, and reliable forecasting of electricity demand and supply is essential for the effective operation of power systems. Accurate forecasts allow power system operators to make informed decisions about generation, transmission, and distribution, which can help to prevent blackouts and other disruptions to the electricity supply. Various methods have been developed for forecasting electricity, including statistical methods such as ARIMA and Prophet and artificial intelligence (AI) algorithms such as recurrent neural network (RNN) and support vector machines (SVM). Recent advances in deep learning, particularly Long Short-Term Memory (LSTM) networks, have demonstrated superior performance for time-series forecasting tasks, especially with high-frequency datasets. In this paper, we compared the performance of six methods covering two statistical and four AI algorithms for forecasting electricity demand. They were applied to four different datasets: 1) A monthly KAPSARC, which stands for The King Abdullah Petroleum Studies and Research Center, Dataset in Saudi Arabia with limited historical data, 2) A generated hourly KAPSARC Dataset in Saudi Arabia, 3) An hourly PJM Dataset in USA with a large amount of data, and 4) A generated monthly PJM Dataset in USA. The performance of the approaches was different with each dataset. Overall, the results confirm that data richness particularly hourly granularity is a decisive factor in forecasting accuracy, and that deep learning models require substantial data volumes to outperform statistical baselines. These findings have direct implications for electricity infrastructure planning in Saudi Arabia under Vision 2030.
Accurate forecast of electricity demand has become essential for modern energy systems, which are Face-off escalating challenges because of industrial expansion, population growth, and the incorporation of renewable energy sources. With the development of machine learning methods, one can now efficiently forecast power consumption with the help of past data. This paper introduces a machine learning-based predictor of power consumption. We analyze various machine learning techniques, i.e., random forest, XGBoost, linear regression for power forecasting, in this work. These models were trained and tested on historical electricity consumption data from the Ministry of Electricity of Iraq, 2022 to 2025. The models' performance was evaluated using a number of metrics, such as Mean Absolute Error, Root Mean Squared Error, Mean absolute percentage error, and R-squared. the best performance model for demand was XGBoost, the model achieved on R-squared value of 0.98 and Linear regression model achieved on R-squared value of 0.98 for supply.
Maryam Jamal Abdulhameed, Ali Hasan Taresh· Iraqi Journal for Computers...· 0 citations
The intermittent and volatile characteristics of new energy generation, together with the increasing demand for stable power supply in intelligent industrial systems, make accurate forecasting a critical issue for grid dispatch and electromagnetic energy management. This study systematically reviews the technological evolution of time series analysis methods for wind and photovoltaic (PV) power forecasting and establishes a comparative framework covering classical statistical models, intelligent learning algorithms, and hybrid modeling strategies. Based on two years of operational data collected from an actual wind farm and PV station in East China, the forecasting performance of ARIMA, exponential smoothing, Support Vector Regression (SVR), Long Short-Term Memory (LSTM) networks, and Transformer architectures is comprehensively evaluated, while hybrid approaches based on Empirical Mode Decomposition (EMD) are further investigated. The results demonstrate that model selection should jointly consider forecasting horizon, data characteristics, and computational constraints. Classical statistical methods remain robust under stable operating conditions but are less effective in capturing extreme fluctuations, whereas deep learning approaches exhibit superior capability in modeling long-range temporal dependencies despite reduced interpretability. Decomposition-based hybrid strategies achieve a more balanced performance across diverse scenarios and show enhanced robustness under extreme weather conditions. The study further proposes a structured model selection guideline by matching data characteristics with operational requirements, providing theoretical support for forecasting system design in renewable-energy-driven power networks and offering useful references for electromagnetic energy utilization and intelligent industrial applications.
M. S. Song, C. Yang, Z. Heng et al.· Advanced Electromagnetics· 0 citations
This article forecasts electricity demand over two-month, one-year, and two-year horizons using 20 years of open-access data from the COES system operator. The proposed approach applies machine learning (ML) algorithms with exogenous variables and optimized LGBMRegressor hyperparameters to reduce forecasting error. Its performance is compared with mathematical statistical models (MSMs), including SARIMAX, ARIMA, and ARIMA with cross-validation. The MSM-based approaches produced lower performance metrics than the ML-based techniques and required longer computational execution times. The implementation was carried out in Google Colab Pro using Python 3.12 and libraries such as skforecast, taking advantage of the available high RAM capacity to reduce the computational time of the two forecasting techniques analyzed. For the two-month forecasting horizon, the lowest mean absolute error (MAE) was achieved with the LGBMRegressor algorithm including exogenous variables and optimized hyperparameters, with a value of 98.69 MW, whereas ARIMA with cross-validation yielded an error of 207.93 MW. These results indicate that the use of ML algorithms for electricity demand forecasting reduces forecasting errors and requires less computational execution time. Therefore, only ML was used for the one-year and two-year forecasting horizons. Based on this result, a one-year forecast was obtained with the LGBMRegressor algorithm, yielding an MAE of 111.77 MW, while the two-year forecast produced an MAE of 96.344 MW. This work incorporated socioeconomic exogenous variables, such as quarterly GDP, population, and access to electricity, which improved the medium-term forecasting model. The resulting forecasts may be useful for both the operation and planning of the electric power system (EPS).
Robinson Reinoso-Acosta, Carlos Barrera-Singaña· Energies· 0 citations
This study compares two multi-step forecasting strategies for 24-h horizons: a direct 24→24 strategy and a recursive strategy based on sequential 24→1 predictions, and concludes that the selection of a forecasting strategy depends on the required balance between overall accuracy, temporal stability, and computational cost.
Erik Fernando Mendez-Garces, David Buldain, M. Comech· Energies· 0 citations
The empirical results indicate that tree-based ensemble models outperform deep learning approaches under the considered dataset conditions and suggest that ensemble machine learning techniques are more suitable for data-constrained environments, where deep learning models may suffer from overfitting.
Lamiaa Fares, Moad El Kharrim, Mohamed Dakkon· 0 citations
Predictive decision analytics is gaining significance for better planning, resource allocation, and optimization of operations in business & industry. The issue of forecasting electricity prices is a relevant one as the volatility of prices directly affects procurement, production scheduling and operating costs. This study developed an artificial intelligence and machine learning framework for predictive decision analytics using electricity price forecasting as the application domain. A publicly available dataset comprising 23,304 observations and 11 variables was analysed. Historical electricity load, lagged electricity prices, day, and season were used as predictors of the current electricity price. Random Forest, XGBoost, and Gradient Boosting models were developed using an 80:20 train–test split. Model performance was evaluated using MAE, RMSE, MAPE, R², five-fold time-series cross-validation, and SHAP-based interpretation. All three models achieved comparable predictive performance. XGBoost produced the highest R² (0.8870) and lowest RMSE (927.43), while Gradient Boosting achieved the lowest MAE (575.34) and MAPE (10.44%). Time-series cross-validation reported a mean R² of 0.7823, confirming stable predictive capability under changing temporal conditions. SHAP analysis identified recent historical electricity prices, particularly P(T−1) and P(T−24), as the most influential predictors. The results prove that ensemble machine learning is a credible and explainable approach to electricity price prediction, which can be utilized for procurement planning, budgeting, production scheduling, and decision-making for business and industry. .
A. Bhargava· Journal of Intelligent Decis...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
